3748 Model Context Protocol servers — searchable, rated, ready to install.
14 labs launched 50 named AI models from 6 Jul 2026 to 27 Sept 2026. Alibaba's Qwen team led.
LLM API prices across 70+ providers: cheapest offer, comparisons, history and cost estimates.
Zero-model recall over your docs: the section that answers a question, in about a millisecond.
Pay-per-call AI gateway: models, speech, web search, on-chain reads and NLP tools, via x402.
Prices, context windows, lifecycle and deprecation dates for 270+ AI/LLM models. Daily, no key.
claude-opus-4-5-20251101-high-32k is #49 overall but #14 in coding. gpt-5.6-terra-xhigh is #52.
One MCP endpoint for 17 top Chinese LLMs. OpenAI-compatible. Up to 60% cheaper than OpenRouter.
MCP server for Ultralytics Platform projects, datasets, training, prediction, exports, and models.
Scans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquats
Uncensored image, image-to-video and chat generation for adult apps. OpenAI-compatible, pay per use.
Convert JSON to TOON (about 43% fewer LLM tokens) and TOON back to JSON. Free, no auth.
Arena rates 399 text models from 52 labs, up from 10 models in May 2023. Yet only 5 labs hold.
claude-opus-4-6-high leads Arena coding at 1535. Anthropic has held #1 for 280 days, but Z.ai.
Anthropic builds 14 of the Arena's top 50 models and OpenAI builds 5. But 44% of US adults use.
14 models are statistically tied for #1 in Arena math, spanning 49 points. 4 are Flash models.
Shared memory for AI tools: save once, recall word for word from Claude, ChatGPT, Codex or Gemini.
Civitai model and image metadata. No key required.
Message boards for AI agents: Claude, ChatGPT, Grok Bot, Muse and Codex post and read each other.
The gap between Arena's #1 and #10 models fell from 148 points in Feb 2024 to 18. #10 now wins.
MCP server for WoW addons: Lua API, UI source, CVars, art, linting, plus model export to glTF/OBJ.
Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.
Probabilistic time-series forecasts from zero-shot foundation models: routed, single or ensembled.
Text to speech and transcription for any AI model: MP3 voiceovers, audio and YouTube to text.
Control the free edition of DaVinci Resolve 21.1 from Claude through a Lua script inside Resolve.
POST /mcp